feat(import): move PDF parsing to backend; fix heartbeat/reap for import_tasks

- parsePDF function restored in import.go (body was orphaned outside function)
- ParseImportFile() called at upload time with 3-min timeout; chapters stored as JSON in MinIO
- runner.go: prefer ChaptersKey path (read pre-parsed JSON) over BookImport.Import()
- ImportChapterStore interface added; store wired in runner/main.go
- HeartbeatTask and ReapStaleTasks now include import_tasks collection
- parseImportTask now returns ChaptersKey in domain.ImportTask
- asynq_runner.go handleImportTask passes ChaptersKey
- pb-init-v3.sh: chapters_key field added to import_tasks schema

backend/internal/backend/handlers_import.go

@@ -1,6 +1,7 @@
 package backend
 
 import (
+	"context"
 	"encoding/json"
 	"fmt"
 	"io"
@@ -45,6 +46,8 @@ func (s *Server) handleAdminImport(w http.ResponseWriter, r *http.Request) {
 	ct := r.Header.Get("Content-Type")
 	var req importRequest
 	var objectKey string
+	var chaptersKey string
+	var chapterCount int
 
 	if strings.HasPrefix(ct, "multipart/form-data") {
 		if err := r.ParseMultipartForm(32 << 20); err != nil {
@@ -96,7 +99,20 @@ func (s *Server) handleAdminImport(w http.ResponseWriter, r *http.Request) {
 			return
 		}
 
-		// Upload to MinIO for actual import
+		// Parse PDF/EPUB on the backend (with timeout) and store chapters as JSON.
+		// The runner only needs to ingest pre-parsed chapters — no PDF parsing on runner.
+		parseCtx, parseCancel := context.WithTimeout(r.Context(), 3*time.Minute)
+		defer parseCancel()
+		chapters, parseErr := storage.ParseImportFile(parseCtx, data, req.FileType)
+		if parseErr != nil || len(chapters) == 0 {
+			jsonError(w, http.StatusUnprocessableEntity, "could not parse file: "+func() string {
+				if parseErr != nil { return parseErr.Error() }
+				return "no chapters found"
+			}())
+			return
+		}
+
+		// Store raw file in MinIO (for reference/re-import).
 		objectKey = fmt.Sprintf("imports/%d_%s", time.Now().Unix(), header.Filename)
 		if s.deps.ImportFileStore == nil {
 			jsonError(w, http.StatusInternalServerError, "storage not available")
@@ -106,6 +122,15 @@ func (s *Server) handleAdminImport(w http.ResponseWriter, r *http.Request) {
 			jsonError(w, http.StatusInternalServerError, "upload file: "+err.Error())
 			return
 		}
+
+		// Store pre-parsed chapters JSON in MinIO so runner can ingest without re-parsing.
+		chaptersJSON, _ := json.Marshal(chapters)
+		chaptersKey = fmt.Sprintf("imports/%d_%s_chapters.json", time.Now().Unix(), strings.TrimSuffix(header.Filename, filepath.Ext(header.Filename)))
+		if err := s.deps.ImportFileStore.PutImportChapters(r.Context(), chaptersKey, chaptersJSON); err != nil {
+			jsonError(w, http.StatusInternalServerError, "store chapters: "+err.Error())
+			return
+		}
+		chapterCount = len(chapters)
 	} else {
 		if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
 			jsonError(w, http.StatusBadRequest, "parse body: "+err.Error())
@@ -141,6 +166,8 @@ func (s *Server) handleAdminImport(w http.ResponseWriter, r *http.Request) {
 		BookStatus:      req.BookStatus,
 		FileType:        req.FileType,
 		ObjectKey:       objectKey,
+		ChaptersKey:     chaptersKey,
+		ChaptersTotal:   chapterCount,
 		InitiatorUserID: "",
 	})
 	if err != nil {
@@ -149,8 +176,9 @@ func (s *Server) handleAdminImport(w http.ResponseWriter, r *http.Request) {
 	}
 
 	writeJSON(w, 0, importResponse{
-		TaskID: taskID,
-		Slug:   slug,
+		TaskID:   taskID,
+		Slug:     slug,
+		Preview: &importPreview{Chapters: chapterCount},
 	})
 }